This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Siemens Corporation. Active years: 2026.
Company Filing History:
Years Active: 2026
Title: Ting-Han Fan: Innovator in Batch Production Reinforcement Learning
Introduction
Ting-Han Fan is a notable inventor based in Princeton, NJ (US). He has made significant contributions to the field of production systems through his innovative patent. His work focuses on enhancing batch production processes using advanced reinforcement learning techniques.
Latest Patents
Ting-Han Fan holds a patent titled "System and method for supporting execution of batch production using reinforcement learning." This computer-implemented method supports the execution of batch production by a production system. It involves acquiring a system state defined by shop floor status, inventory status, and product demand. The method processes this system state using a reinforcement learned policy, which includes a deep learning model. The output is a control action that defines an integer batch size for a selected product type. The control action is determined by using learned parameters of the deep learning model to compute logits for a categorical distribution of predicted product types and batch sizes. This innovative approach transforms the predicted distributions into actionable insights for production.
Career Highlights
Ting-Han Fan is currently employed at Siemens Corporation, where he applies his expertise in reinforcement learning to improve production efficiency. His work has the potential to revolutionize how batch production is managed in various industries.
Collaborations
Ting-Han Fan collaborates with Yubo Wang, contributing to advancements in their field through shared knowledge and expertise.
Conclusion
Ting-Han Fan's innovative approach to batch production through reinforcement learning exemplifies the impact of technology on manufacturing processes. His contributions are paving the way for more efficient production systems in the future.